A method for surveying and mapping complex terrain during surveying and mapping

Abstract

The present invention discloses a method for surveying and mapping complex terrain in the surveying and mapping process, and relates to the field of surveying and mapping technology. The present invention constructs a convolutional neural network model, and trains the method for dividing the entire area into sub-areas, terrain complexity data, terrain complexity level data, and a preset surveying and mapping method as a training set. By using the trained convolutional neural network model, it is only necessary to obtain remote sensing satellite image data of the area to be surveyed and mapped, and the area can be automatically divided into sub-areas, and the terrain complexity level and corresponding surveying and mapping method of each sub-area can be output at the same time, while ensuring the accuracy of complex terrain surveying and mapping, the surveying and mapping efficiency of the entire area is improved. At the same time, the surveying and mapping data of each sub-area is obtained in real time and transmitted back to a preset ground platform; the preset ground platform processes all surveying and mapping data, thereby improving the processing efficiency of surveying and mapping data.

Description

Technical Field

[0001] The present invention relates to the field of surveying and mapping technology, and in particular to a method for surveying and mapping complex terrain during a surveying and mapping process. Background Art

[0002] In modern society, surveying and mapping technology plays an important role in urban planning, land management, environmental protection and other fields. However, in the process of surveying and mapping complex terrain, there have always been the following pain points: 1) The diverse terrain changes lead to inaccurate data. Complex terrain often contains various forms such as mountains, hills, and canyons. The diversity of terrain changes has brought great challenges to surveying and mapping. Traditional measurement methods are difficult to accurately capture subtle changes in terrain, resulting in inaccurate surveying and mapping data; 2) Problems with drone surveying and mapping. In recent years, drone surveying and mapping has become a common surveying and mapping technology. However, in complex terrain, drone surveying and mapping also has some problems, such as poor adaptability to complex terrain and easy to be restricted by geographical conditions such as undulating terrain and cliffs; 3) Challenges in data processing. The amount of data generated in the surveying and mapping process of complex terrain is huge. Traditional data processing methods often cannot meet the needs of surveying and mapping data. The speed and accuracy of data processing have become a major problem in complex terrain surveying and mapping; 4) The single surveying and mapping form leads to low overall surveying and mapping efficiency. Summary of the invention

[0003] In order to solve the deficiencies of the prior art, the present invention provides a method for surveying and mapping complex terrain during the surveying and mapping process, the method comprising the following steps:

[0004] Based on the GPS system, the area to be surveyed is located to obtain the positioning result;

[0005] Based on the positioning result, remote sensing satellite image data of the area to be surveyed and mapped is acquired to obtain a plurality of initial survey area images of the area to be surveyed and mapped;

[0006] Dividing the area to be surveyed into a plurality of sub-areas, and setting the terrain complexity for each sub-area based on all the initial survey area images;

[0007] The terrain complexity is classified into different levels, and the corresponding terrain complexity level is obtained by acquiring the terrain complexity of each sub-area;

[0008] For each level of terrain complexity, a corresponding surveying and mapping method is preset;

[0009] Constructing a convolutional neural network model for the area to be surveyed, and inputting the sub-area division method of the area to be surveyed, all terrain complexity data, all terrain complexity level data and all preset surveying methods as a training set into the convolutional neural network model for training;

[0010] Acquire remote sensing satellite image data in the area to be surveyed and input it into the trained convolutional neural network model, and output a corresponding surveying and mapping method;

[0011] Based on the outputted surveying and mapping method, surveying and mapping work is performed on the area to be surveyed and mapped.

[0012] The present invention is implemented through the following technical scheme: This scheme first uses the GPS system (global positioning system) to perform regional positioning of the area to be surveyed. After positioning, remote sensing satellite image data in the area is obtained to obtain multiple initial survey area images of the area to be surveyed. Then the entire area to be surveyed is divided into multiple sub-areas, and the surveying and mapping work of the entire area is converted into the surveying and mapping work of multiple sub-areas. The advantage is that different surveying and mapping methods can be used or different parameters can be set for different sub-areas, which improves the surveying and mapping efficiency while ensuring the surveying and mapping accuracy. Based on all the initial surveying and mapping area images, the terrain complexity is set for each sub-area, the terrain complexity is further limited, the corresponding terrain complexity level is set, and the corresponding surveying and mapping method is preset for each terrain complexity level. Finally, by constructing a convolutional neural network model, all terrain complexity data, all terrain complexity level data and preset surveying and mapping methods are input as training sets into the convolutional neural network model for training. When a new area needs to be surveyed again, it is only necessary to input the remote sensing satellite image data of the new area into the trained convolutional neural network model to automatically divide the area, output the terrain complexity level and corresponding surveying method of each sub-area, and then survey and map the corresponding sub-area based on the output surveying method.

[0013] The present invention constructs a convolutional neural network model, and uses the method of dividing the entire area into sub-regions, terrain complexity data, terrain complexity level data and a preset surveying and mapping method as a training set for training. By using the trained convolutional neural network model, it is only necessary to obtain remote sensing satellite image data of the area to be surveyed to automatically divide the area into sub-regions, and simultaneously output the terrain complexity level and corresponding surveying and mapping method of each sub-region, thereby improving the surveying and mapping efficiency of the overall area while ensuring the accuracy of complex terrain surveying and mapping.

[0014] As an optional technical solution, dividing the area to be surveyed into several sub-areas includes:

[0015] Acquire a plan view of the area to be surveyed and mapped, and based on the plan view, preliminarily divide the area to be surveyed and mapped into a plurality of initial sub-areas according to preset rectangles;

[0016] Traverse all initial sub-regions to determine whether the surveying and mapping object contained in a single initial sub-region is complete. If so, do not take any action. If not, record the incomplete surveying and mapping object as the first surveying and mapping object.

[0017] Acquire all initial sub-regions containing the first surveying object and put them into a preset set, and select the initial sub-region containing the largest area of ​​the first surveying object from the preset set and record it as the first initial sub-region;

[0018] retaining the first initial sub-region, and adjusting all initial sub-regions in the preset set except the first initial sub-region;

[0019] The adjusted first initial sub-region is recorded as the first sub-region.

[0020] As an optional technical solution, adjusting all initial sub-regions in the preset set except the first initial sub-region includes:

[0021] All initial sub-regions except the first initial sub-region in the preset set divide the region including the first surveying object into the first initial sub-region to obtain the first sub-region.

[0022] As an optional technical solution, based on all the initial survey area images, the terrain complexity is set for each sub-area including:

[0023] The terrain complexity of each sub-area is calculated using the following formula:

[0024]

[0025] is the terrain complexity of each sub-area, is the terrain complexity of the surface type of a single sub-region, is the terrain complexity of the vegetation type in a single sub-area.

[0026] As an optional technical solution, obtaining the terrain complexity of the surface type includes:

[0027]

[0028] is the complexity coefficient of different surface types, For different surface types, The value of is a constant A, and m is the number of surface types.

[0029] As an optional technical solution, obtaining the terrain complexity of the vegetation type includes:

[0030]

[0031] is the complexity coefficient of different vegetation types, For different vegetation types, The value of is a constant B, and r is the number of vegetation types.

[0032] As an optional technical solution, obtaining the terrain complexity of each sub-area to obtain the corresponding terrain complexity level includes:

[0033] Obtain historical data on terrain complexity;

[0034] Based on the historical data, the terrain complexity is divided into intervals, and each interval corresponds to a different terrain complexity level.

[0035] As an optional technical solution, the terrain complexity level is divided into levels I, II and III.

[0036] As an optional technical solution, for each level of terrain complexity, corresponding mapping methods are preset, including:

[0037] When the terrain complexity level is level I, the first method is used to map the area to be mapped, and the first method is specifically: obtaining remote sensing satellite image data of the area to be mapped, processing the remote sensing satellite image data as first mapping data of the corresponding sub-area, and mapping the corresponding sub-area based on the first mapping data;

[0038] When the terrain complexity level is level II, the second method is used to map the area to be mapped, and the second method is specifically: setting a first cruising path and a first working parameter for the UAV, based on the first cruising path and the first working parameter, the UAV obtains second mapping data of the corresponding sub-area, and based on the second mapping data, maps the corresponding sub-area;

[0039] When the terrain complexity level is level III, a third method is used to survey the area to be surveyed. The third method is specifically: a second cruise path and a second working parameter are set for the UAV. Based on the second cruise path and the second working parameter, the UAV obtains third surveying and mapping data of the corresponding sub-area, and based on the third surveying and mapping data, the corresponding sub-area is surveyed and mapped.

[0040] As an optional technical solution, the method further includes: acquiring surveying and mapping data of each sub-area in real time and transmitting the data back to a preset ground platform; and the preset ground platform processes all surveying and mapping data.

[0041] One or more technical solutions provided by the present invention have at least the following technical effects or advantages:

[0042] The present invention discloses a method for surveying and mapping complex terrain in a surveying and mapping process. By constructing a convolutional neural network model, a method for dividing the entire area into sub-areas, terrain complexity data, terrain complexity level data and a preset surveying and mapping method are used as a training set for training. By using the trained convolutional neural network model, it is only necessary to obtain remote sensing satellite image data of the area to be surveyed and mapped to automatically divide the area into sub-areas, and simultaneously output the terrain complexity level and the corresponding surveying and mapping method of each sub-area, thereby improving the surveying and mapping efficiency of the overall area while ensuring the surveying and mapping accuracy of complex terrain. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of the present invention, and do not constitute a limitation on the embodiments of the present invention;

[0044] Figure 1 It is a schematic flow chart of a method for surveying and mapping complex terrain during a surveying and mapping process in the present invention. DETAILED DESCRIPTION

[0045] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0046] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those within the scope of this description. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0047] Example

[0048] Please refer to Figure 1 , Figure 1 The present invention provides a method for surveying and mapping complex terrain during a surveying and mapping process, and the method comprises the following steps:

[0049] Based on the GPS system, the area to be surveyed is located to obtain the positioning result;

[0050] Based on the positioning result, remote sensing satellite image data of the area to be surveyed and mapped is acquired to obtain a plurality of initial survey area images of the area to be surveyed and mapped;

[0051] Dividing the area to be surveyed into a plurality of sub-areas, and setting the terrain complexity for each sub-area based on all the initial survey area images;

[0052] The terrain complexity is classified into different levels, and the corresponding terrain complexity level is obtained by acquiring the terrain complexity of each sub-area;

[0053] For each level of terrain complexity, a corresponding surveying and mapping method is preset;

[0054] Constructing a convolutional neural network model for the area to be surveyed, and inputting the sub-area division method of the area to be surveyed, all terrain complexity data, all terrain complexity level data and all preset surveying methods as a training set into the convolutional neural network model for training;

[0055] Acquire remote sensing satellite image data in the area to be surveyed and input it into the trained convolutional neural network model, and output a corresponding surveying and mapping method;

[0056] Based on the outputted surveying and mapping method, surveying and mapping work is performed on the area to be surveyed and mapped.

[0057] The specific embodiment of the present invention is as follows: the area to be surveyed is located by a GPS (global positioning system) to obtain a positioning result, and based on the positioning result, remote sensing satellite image data of the area to be surveyed is obtained to obtain a plurality of initial survey area images of the area to be surveyed. The area to be surveyed is then divided into sub-areas, which is specifically manifested as follows:

[0058] Acquire a plan view of the area to be surveyed and mapped, and based on the plan view, preliminarily divide the area to be surveyed and mapped into a plurality of initial sub-areas according to preset rectangles;

[0059] Traverse all initial sub-regions to determine whether the surveying and mapping object contained in a single initial sub-region is complete. If so, do not take any action. If not, record the incomplete surveying and mapping object as the first surveying and mapping object.

[0060] Acquire all initial sub-regions containing the first surveying object and put them into a preset set, and select the initial sub-region containing the largest area of ​​the first surveying object from the preset set and record it as the first initial sub-region;

[0061] retaining the first initial sub-region, and adjusting all initial sub-regions in the preset set except the first initial sub-region;

[0062] The adjusted first initial sub-region is recorded as the first sub-region.

[0063] Adjusting all initial sub-areas in the preset set except the first initial sub-area includes:

[0064] All initial sub-regions except the first initial sub-region in the preset set divide the region including the first surveying object into the first initial sub-region to obtain the first sub-region.

[0065] Among them, the method for obtaining the plan map can be obtained by stitching and calibrating multiple initial survey area images. The core idea of ​​dividing the entire area to be surveyed into multiple sub-areas is to perform a two-step division. The first step is to divide the entire area into multiple identical areas, and the second step is to determine whether the divided sub-areas contain complete survey objects. For example, if there is a lake in the area to be surveyed, after the first step of division, the lake is included in multiple sub-areas (C, D and E). This obviously has a great impact on the subsequent calculation of the terrain complexity of each sub-area. Therefore, this example counts the area size of the lake in sub-area C, sub-area D and sub-area E. If the area of ​​the lake in sub-area C is the largest, sub-area C will be retained, and the area of ​​the lake in sub-area D and sub-area E will be divided into sub-area C.

[0066] Based on all the initial survey area images, the terrain complexity is set for each sub-area, which is as follows:

[0067] The terrain complexity of each sub-area is calculated using the following formula:

[0068]

[0069] is the terrain complexity of each sub-area, is the terrain complexity of the surface type of a single sub-region, is the terrain complexity of the vegetation type in a single sub-area.

[0070] Acquiring the terrain complexity of the surface type includes:

[0071]

[0072] is the complexity coefficient of different surface types, For different surface types, The value of is a constant A, and m is the number of surface types.

[0073] Acquiring the terrain complexity of the vegetation type includes:

[0074]

[0075] is the complexity coefficient of different vegetation types, For different vegetation types, The value of is a constant B, and r is the number of vegetation types.

[0076] In the process of mapping complex terrain, the difficulty of mapping mainly comes from the mapping restrictions brought by different surface types and vegetation types. Therefore, when setting the terrain complexity for each sub-area, this embodiment mainly reflects it through the surface complexity value and the vegetation complexity value. The mapping difficulties corresponding to different surfaces and different vegetation are also different. Therefore, this embodiment sets different complexity coefficients for different surfaces and vegetation. The complexity coefficient can be calibrated by analyzing and processing the historical mapping data in the past, and this embodiment does not make specific restrictions. In addition, in this embodiment, since the mapping difficulty brought by the surface is much greater than that of vegetation, the value of constant A is limited to be greater than the value of constant B.

[0077] After setting the terrain complexity for each sub-area, the corresponding terrain complexity level is obtained, which is specifically expressed as follows:

[0078] Obtain historical data on terrain complexity;

[0079] Based on the historical data, the terrain complexity is divided into intervals, and each interval corresponds to a different terrain complexity level.

[0080] By obtaining historical data on terrain complexity and combining it with past surveying and mapping data, the terrain complexity is divided into intervals, and each interval corresponds to a different level of terrain complexity. For example, the terrain complexity level is divided into levels I, II, and III. The division of terrain complexity levels can be adjusted according to actual conditions.

[0081] For different levels of terrain complexity, corresponding surveying and mapping methods are preset, which are as follows:

[0082] When the terrain complexity level is level I, the first method is used to map the area to be mapped, and the first method is specifically: obtaining remote sensing satellite image data of the area to be mapped, processing the remote sensing satellite image data as first mapping data of the corresponding sub-area, and mapping the corresponding sub-area based on the first mapping data;

[0083] When the terrain complexity level is level II, the second method is used to map the area to be mapped, and the second method is specifically: setting a first cruising path and a first working parameter for the UAV, based on the first cruising path and the first working parameter, the UAV obtains second mapping data of the corresponding sub-area, and based on the second mapping data, maps the corresponding sub-area;

[0084] When the terrain complexity level is level III, a third method is used to survey the area to be surveyed. The third method is specifically: a second cruise path and a second working parameter are set for the UAV. Based on the second cruise path and the second working parameter, the UAV obtains third surveying and mapping data of the corresponding sub-area, and based on the third surveying and mapping data, the corresponding sub-area is surveyed and mapped.

[0085] When the terrain complexity level is level I, it means that the mapping difficulty is very low at this time. For example, for a single surface type or vegetation type (such as grassland or lake, etc.), it is only necessary to obtain remote sensing satellite image data as the first mapping data, and use the first mapping data to map the corresponding sub-area. When the terrain complexity level is level II, the mapping difficulty increases at this time, and it is necessary to use drones and other aerial survey equipment to assist in the acquisition of mapping data. At the same time, it is necessary to set the cruise path and working parameters for the drone, where the cruise path and working parameters can be calibrated through historical mapping data. When the terrain complexity level is level III, it means that the mapping difficulty is huge at this time. If only drones and other aerial survey equipment are used to acquire mapping data, the mapping accuracy is not high. When setting the working parameters for the drone, multiple laser radars are configured for the drone, so that when the drone acquires mapping data, it no longer only acquires aerial survey image data, but also needs to acquire laser radar data to solve the problem that the drone cannot acquire the corresponding aerial survey image due to terrain problems. Similarly, the cruise path and working parameters can be calibrated through historical mapping data, which is not specifically limited in this embodiment.

[0086] Finally, by constructing a convolutional neural network model, all terrain complexity data, all terrain complexity level data and preset mapping methods are input into the convolutional neural network model as training sets for training. When a new area needs to be mapped again, it is only necessary to input the remote sensing satellite image data of the new area into the trained convolutional neural network model to automatically divide the area, and output the terrain complexity level and corresponding mapping method of each sub-area, and then map the corresponding sub-area based on the output mapping method.

[0087] Furthermore, in order to address the problem of low data processing speed, the present embodiment also provides a method for processing surveying and mapping data. In the past, due to the excessive amount of surveying and mapping data collected, it was necessary to wait until the surveying and mapping task was completed before processing all the surveying and mapping data. However, in the present embodiment, the amount of surveying and mapping data that needs to be collected in each sub-area is greatly reduced, under the premise of dividing the entire surveying and mapping area into sub-areas and setting a surveying and mapping method for each sub-area. Therefore, the present embodiment can obtain the surveying and mapping data of each sub-area in real time and transmit it back to the ground preset platform; the ground preset platform processes all the surveying and mapping data.

[0088] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0089] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for surveying complex terrain during surveying, characterized in that: The method comprises the following steps: Based on the GPS system, the area to be surveyed is located to obtain the positioning result; Based on the positioning result, remote sensing satellite image data of the area to be surveyed and mapped is acquired to obtain a plurality of initial survey area images of the area to be surveyed and mapped; Dividing the area to be surveyed into a plurality of sub-areas, and setting the terrain complexity for each sub-area based on all the initial survey area images; The terrain complexity is classified into different levels, and the corresponding terrain complexity level is obtained by acquiring the terrain complexity of each sub-area; For each level of terrain complexity, a corresponding surveying and mapping method is preset; Constructing a convolutional neural network model for the area to be surveyed, and inputting the sub-area division method of the area to be surveyed, all terrain complexity data, all terrain complexity level data and all preset surveying methods as a training set into the convolutional neural network model for training; Acquire remote sensing satellite image data in the area to be surveyed and input it into the trained convolutional neural network model, and output a corresponding surveying and mapping method; Based on the outputted surveying and mapping method, surveying and mapping work is performed on the area to be surveyed and mapped.

2. The method for surveying and mapping complex terrain in the surveying and mapping process according to claim 1, characterized in that: Dividing the area to be surveyed into several sub-areas includes: Acquire a plan view of the area to be surveyed and mapped, and based on the plan view, preliminarily divide the area to be surveyed and mapped into a plurality of initial sub-areas according to preset rectangles; Traverse all initial sub-regions to determine whether the surveying and mapping object contained in a single initial sub-region is complete. If so, do not take any action. If not, record the incomplete surveying and mapping object as the first surveying and mapping object. Acquire all initial sub-regions containing the first surveying object and put them into a preset set, and select the initial sub-region containing the largest area of ​​the first surveying object from the preset set and record it as the first initial sub-region; retaining the first initial sub-region, and adjusting all initial sub-regions in the preset set except the first initial sub-region; The adjusted first initial sub-region is recorded as the first sub-region.

3. The method for surveying and mapping complex terrain in the surveying and mapping process according to claim 2, characterized in that: Adjusting all initial sub-areas in the preset set except the first initial sub-area includes: All initial sub-regions except the first initial sub-region in the preset set divide the region including the first surveying object into the first initial sub-region to obtain the first sub-region.

4. The method for surveying and mapping complex terrain in a surveying and mapping process according to claim 1, characterized in that: Based on all the initial survey area images, the terrain complexity is set for each sub-area including: The terrain complexity of each sub-area is calculated using the following formula: is the terrain complexity of each sub-area, is the terrain complexity of the surface type of a single sub-region, is the terrain complexity of the vegetation type in a single sub-area.

5. The method for surveying and mapping complex terrain in the surveying and mapping process according to claim 4, characterized in that: Acquiring the terrain complexity of the surface type includes: is the complexity coefficient of different surface types, For different surface types, The value of is a constant A, and m is the number of surface types.

6. The method for surveying and mapping complex terrain in the surveying and mapping process according to claim 4, characterized in that: Acquiring the terrain complexity of the vegetation type includes: is the complexity coefficient of different vegetation types, For different vegetation types, The value of is a constant B, and r is the number of vegetation types.

7. The method for surveying and mapping complex terrain in the surveying and mapping process according to claim 1, characterized in that: Obtaining the terrain complexity of each sub-area to obtain the corresponding terrain complexity level includes: Obtain historical data on terrain complexity; Based on the historical data, the terrain complexity is divided into intervals, and each interval corresponds to a different terrain complexity level.

8. The method for surveying and mapping complex terrain in the surveying and mapping process according to claim 7, characterized in that: The terrain complexity levels are divided into levels I, II and III.

9. The method for surveying and mapping complex terrain in the surveying and mapping process according to claim 8, characterized in that: For each level of terrain complexity, corresponding surveying and mapping methods are preset, including: When the terrain complexity level is level I, the first method is used to map the area to be mapped, and the first method is specifically: obtaining remote sensing satellite image data of the area to be mapped, processing the remote sensing satellite image data as first mapping data of the corresponding sub-area, and mapping the corresponding sub-area based on the first mapping data; When the terrain complexity level is level II, the second method is used to map the area to be mapped, and the second method is specifically: setting a first cruising path and a first working parameter for the UAV, based on the first cruising path and the first working parameter, the UAV obtains second mapping data of the corresponding sub-area, and based on the second mapping data, maps the corresponding sub-area; When the terrain complexity level is level III, a third method is used to survey the area to be surveyed. The third method is specifically: a second cruise path and a second working parameter are set for the UAV. Based on the second cruise path and the second working parameter, the UAV obtains third surveying and mapping data of the corresponding sub-area, and based on the third surveying and mapping data, the corresponding sub-area is surveyed and mapped.

10. The method for surveying and mapping complex terrain in the surveying and mapping process according to claim 9, characterized in that: The method further includes: acquiring surveying and mapping data of each sub-area in real time and transmitting the data back to a preset ground platform; and the preset ground platform processes all surveying and mapping data.

Images